Fardina Alam
Fardina Alam
Lecturer, Computer Science
I am a Lecturer in the Department of Computer Science and Program Director for the Data Science M.S. and Certificate programs in the Science Academy, CMNS at UMD. I teach undergraduate and graduate data science courses across both the department and the Science Academy. My research focuses on advancing machine learning and computational biology, with a growing interest in ethical AI in data science education. In 2025, I also served as Administrative and Academic Lead for the Break Through Tech Instructional Hub, collaborating with Cornell Tech’s Break Through Tech AI program to broaden access to AI education.
My primary research focus on developing generative AI models to learn and sample protein tertiary structures, linking structure to function and generating realistic models beyond static views.
My research also explores the integration of Artificial Intelligence (AI) tools into academic courses, focusing on their potential benefits for students and the overall learning process.
Latest Papers
ConSOLAE: Learning Smooth and Generalizable Representations for Protein Fold Recognition
Author(s): Shraddha Patre, Riya Kanani, Aarnav Tare, et. al
RAGent: A Self-Learning RAG Agent for Adaptive Data Science Education
|
International Computer Programming Education Conference (ICPEC)
Author(s): Mariia Vetluzhskikh, Fardina Fathmiul Alam
SuperFoldAE: Enhancing Protein Fold Classification with Autoencoders
Author(s): Shraddha Patre, Riya Kanani, Fardina Fathmiul Alam
Equivariant Encoding based GVAE (EqEn-GVAE) for Protein Tertiary Structure Generation
|
2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Author(s): Taseef Rahman, Fardina Fathmiul Alam, Amarda Shehu
Data Size and Quality Matter: Generating Physically-Realistic Distance Maps of Protein Tertiary Structures
|
Biomolecules
Author(s): Fardina Fathmiul Alam, Amarda Shehu
Deep Latent-Variable Models for Controllable Molecule Generation
|
2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Author(s): Yuanqi Du, Yinkai Wang, Fardina Alam, et. al
Generating Physically-Realistic Tertiary Protein Structures with Deep Latent Variable Models Learning Over Experimentally-available Structures
|
2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Author(s): Fardina Fathmiul Alam, Amarda Shehu
Unsupervised multi-instance learning for protein structure determination
|
Journal of Bioinformatics and Computational Biology
Author(s): Fardina Fathmiul Alam, Amarda Shehu
Towards more equitable question answering systems: How much more data do you need?
|
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
Author(s): Arnab Debnath, Navid Rajabi, Fardina Fathmiul Alam, et. al
Variational Autoencoders for Protein Structure Prediction
|
Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics
Author(s): Fardina Fathmiul Alam, Amarda Shehu